Drowning Judgment System

Abstract

To provide a drowning determination system capable of highly reliably discovering a drowning person or an almost drowning person over a wide range while extremely reducing labor of a user in video monitoring.SOLUTION: A drowning determination system 1 includes: a storage section 2 for storing a plurality of patterns of a vertical change of an exposure part of a person on a water over side when the person is drowning underwater; a detection section 3 for detecting the exposure part of the object person on the water over side, which appears on a set of time-series images obtained by photographing a water surface by a photographing device (drone); a determination section 4 for determining whether the object person A is drowning / almost drowning or not based on the vertical change of the exposure part detected by the set of time-series images with referring to the storage section 2; and a notification section 5 for outputting a notification signal when the determination section 4 determines that the object person is drowning or almost drowning.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a drowning determination system that can detect drowning or drowning-prone people over a wide area with high certainty while significantly reducing the user's effort in video monitoring. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there has been known an in-pool imaging system that is attached to the course ropes of a pool and captures an area adjacent to the course ropes (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-061139 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned technology cannot fully function in places such as the ocean where there are no course ropes and where wide areas must be monitored.

[0005] Therefore, the present invention aims to provide a drowning determination system that can detect drowning or drowning people over a wide area with high certainty while significantly reducing the effort required of users to monitor videos. [Means for solving the problem]

[0006] The present invention provides a drowning determination system comprising: a memory unit that stores multiple patterns of changes in the exposed part of a human above the water when the human is drowning underwater; a detection unit that detects the exposed part of the human subject above the water in a series of time-series images taken of the water surface by an imaging device; a judgment unit that refers to the memory unit and determines whether the human subject is drowning or about to drown based on the changes in the exposed part in the series of time-series images; and an alarm unit that outputs an alarm signal when the judgment unit determines that the human subject is drowning or about to drown.

[0007] According to such a configuration, it is possible to detect a drowning person or a person who is about to drown with a high degree of certainty based on the drowning-specific features. In addition, since it is automatically determined whether the target person is drowning or about to drown, the user's effort in video surveillance is significantly reduced. In addition, by using a detection unit with high detection accuracy, it is possible to detect drowning that occurs far away and cannot be detected by the human eye. Furthermore, by using multiple imaging devices to capture multiple different water surfaces or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal surveillance.

[0008] According to another aspect of the present invention, there is provided a drowning determination program which is installed in a computer in which multiple patterns of changes in the exposed part of a human above the water when the human is drowning in water are stored, the drowning determination program comprising the steps of: detecting the exposed part of a human subject above the water in a series of time-series images taken of the water surface by an image capture device; referring to the computer, determining whether the human subject is drowning or about to drown based on the changes in the exposed part in the series of time-series images; and outputting an alarm signal when it is determined that the human subject is drowning or about to drown.

[0009] According to another aspect of the present invention, a drowning determination system is provided which comprises: a memory unit which stores the speed or size of waves that pose a high risk of a human being being swept away and drowning; a detection unit which detects waves heading toward the coastline captured in a series of time-series images of the water surface taken by an imaging device, and a target human being located between the waves and the coastline; a calculation unit which calculates a predicted speed or predicted size of the waves detected in the series of time-series images when they reach the target human; a judgment unit which refers to the memory unit and determines whether the target human is at high risk of being swept away by waves and drowning based on the calculated predicted speed or predicted size; and an alarm unit which outputs an alarm signal if the judgment unit determines that the risk is high.

[0010] According to this configuration, since the "predicted speed and predicted size when the detected wave reaches the target human" that is difficult to distinguish with the human eye is determined, it is possible to detect with high certainty a human who is at high risk of being swept away by the wave and drowning. In addition, since it is automatically determined whether the target human is at high risk of being swept away by the wave and drowning, the user's labor in video surveillance is significantly reduced. In addition, by using a detection unit with high detection accuracy, it is possible to detect drowning that occurs in a distant place that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal surveillance.

[0011] According to another aspect of the present invention, there is provided a drowning determination program, which is installed in a computer in which the speed or size of waves that pose a high risk of a human being being swept away and drowning is stored, and which comprises the steps of: detecting waves heading toward the coastline in a series of time-series images taken of the water surface by an image capture device, and a target human being located between the waves and the coastline; calculating a predicted speed or predicted size when the waves detected in the series of time-series images reach the target human; referring to the computer, determining whether or not the target human is at high risk of being swept away by the waves and drowning based on the calculated predicted speed or predicted size; and outputting an alarm signal if the determination unit determines that the risk is high.

[0012] According to another aspect of the present invention, a drowning determination system is provided which comprises a detection unit which detects a pair of currents flowing toward the coastline and a target human exposed from the water surface in a series of time-series images taken of the water surface by an imaging device, a judgment unit which determines that the target human is at risk of being swept away by a rip current occurring between the pair of currents if the detected target human is located between the pair of currents and the distance between the pair of currents is within a predetermined distance, and an alarm unit which outputs an alarm signal when the judgment unit determines that there is a risk.

[0013] According to this configuration, it is possible to grasp the occurrence of a rip current F2 that is difficult to distinguish with the human eye, and therefore it is possible to detect with high certainty a person who is at risk of being swept away by a rip current. In addition, since it is automatically determined whether or not a target person is at risk of being swept away by a rip current, the labor of video surveillance by the user is significantly reduced. In addition, by using a detection unit with high detection accuracy, it is possible to detect a rip current that occurs far away that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect a rip current that occurs in a place that cannot be detected by normal surveillance.

[0014] According to another aspect of the present invention, a drowning detection program is provided, which comprises the steps of: detecting a pair of currents heading toward the coastline and a target human exposed from the water surface in a series of time-series images taken of the water surface by an imaging device; determining that the target human is at risk of being swept away by a rip current occurring between the pair of currents if the detected target human is located between the pair of currents and the distance between the pair of currents is within a predetermined distance; and outputting an alarm signal if the determination unit determines that there is a risk.

[0015] According to another aspect of the present invention, a drowning determination system is provided which comprises: a memory unit which stores multiple patterns of ripples or bubbles on the water surface around a human when the human is drowning in water in relation to the position of the human; a detection unit which detects the exposed portion of the target human above the water and the ripples or bubbles on the water surface around the exposed portion in a series of time-series images of the water surface taken by an imaging device; a judgment unit which refers to the memory unit and determines whether the target human is drowning or is about to drown based on the position of the exposed portion and the ripples or bubbles detected in the series of time-series images; and an alarm unit which outputs an alarm signal when the judgment unit determines that the target human is drowning or is about to drown.

[0016] According to this configuration, it is possible to detect a drowning person or a person who is about to drown with high certainty based on ripples or bubbles on the water surface around the person, which occur with a high probability when the person is drowning. In addition, since it is automatically determined whether the target person is drowning or about to drown, the user's effort in video surveillance is significantly reduced. In addition, by using a detection unit with high detection accuracy, it is possible to detect drowning that occurs at a distance that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal surveillance.

[0017] According to another aspect of the present invention, there is provided a drowning determination program which is installed in a computer in which multiple patterns of ripples or bubbles on the water surface around a human relative to the position of the human when the human is drowning in water are stored, the drowning determination program comprising the steps of: detecting the exposed portion of the target human above the water and the ripples or bubbles on the water surface surrounding the exposed portion, which are captured in a series of time-series images of the water surface taken by an image capture device; referring to the computer, determining whether the target human is drowning or about to drown based on the position of the exposed portion and the ripples or bubbles detected in the series of time-series images; and outputting an alarm signal when the determination unit determines that the target human is drowning or about to drown. Effect of the Invention

[0018] According to the drowning determination system of the present invention, it is possible to detect drowning or drowning-prone people over a wide area with high certainty while significantly reducing the effort required of the user to monitor video. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is an explanatory diagram of a usage state of a drowning determination system according to a first embodiment of the present invention; [Diagram 2] Block diagram of a drowning determination system according to a first embodiment of the present invention. [Diagram 3] 1 is a flowchart of a drowning determination system according to a first embodiment of the present invention. [Figure 4] FIG. 13 is an explanatory diagram of a usage state of the drowning determination system according to the second embodiment of the present invention. [Diagram 5] Block diagram of a drowning determination system according to a second embodiment of the present invention. [Figure 6] 1 is a flowchart of a drowning determination system according to a second embodiment of the present invention. [Figure 7] FIG. 13 is an explanatory diagram of a usage state of the drowning determination system according to the third embodiment of the present invention. [Figure 8]Block diagram of a drowning determination system according to a third embodiment of the present invention. [Figure 9] 11 is a flowchart of a drowning determination system according to a third embodiment of the present invention. [Figure 10] FIG. 13 is an explanatory diagram of a usage state of the drowning determination system according to the fourth embodiment of the present invention. [Figure 11] Block diagram of a drowning determination system according to a fourth embodiment of the present invention. [Figure 12] 11 is a flowchart of a drowning determination system according to a fourth embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, a drowning determination system 1 according to an embodiment of the present invention will be described with reference to Figs. 1 to 3.

[0021] The drowning determination system 1 is for detecting a drowning person or a person who is likely to drown from an image of the water surface. In this embodiment, as shown in Fig. 1, an example will be described in which a drowning person A who is likely to drown is detected in approximately real time from an image (a series of time-series images X) of a wide area of ​​the sea surface captured by a drone D.

[0022] The drowning determination system 1 includes a storage unit 2, a detection unit 3, a determination unit 4, and a notification unit 5, as shown in FIG.

[0023] The memory unit 2 stores a plurality of patterns of changes in the up-down direction of the exposed part of a person above water when the person is drowning in water.

[0024] Possible patterns of changes in the exposed parts in the up and down direction include "repeatedly exposing only the head and then exposing the neck at high speed," "repeatedly exposing only the head and then exposing the chest at medium speed," and "exposing up to the neck with almost no up and down movement," etc.

[0025] In addition, in this embodiment, the multiple patterns of changes in the vertical direction of the person's exposed parts above the water include multiple patterns of changes in the vertical direction of the person's arms exposed above the water surface.

[0026] Possible patterns of changes in the up and down direction of the arms include "repeated exposure and submersion of the arms at high speed (while flapping)", "repeated exposure and submersion of the arms at medium speed (while flapping)", "the arms are not exposed", etc.

[0027] The storage unit 2 may further store a plurality of patterns of horizontal changes in the exposed part of the human body above water.

[0028] The detection unit 3 detects the exposed portion of the target human A above the water that is reflected in a series of time-series images X of the water surface captured by an imaging device (drone D).

[0029] This detection may be performed using well-known posture determination techniques, tracking techniques, etc. It is preferable that the detection unit 3 obtains a series of time-series images X in approximately real time, and performs the above detection in approximately real time.

[0030] In addition, the boundary between the exposed part of human A above the water and the sea surface can be determined based on the color boundary (the sea surface is blue, and humans are skin or hair color, etc.).

[0031] The determination unit 4 refers to the storage unit 2 and determines whether the target human A is drowning or about to drown based on the change in the vertical direction of the exposed part detected in the series of time-series images X. In detail, when there is one among the multiple patterns stored in the storage unit 2 that has a predetermined degree of agreement or higher with the change in the vertical direction of the detected exposed part, it is determined that "the target human A is drowning or about to drown."

[0032] The notification unit 5 outputs a notification signal indicating danger when it is determined that "target human A is drowning or about to drown." The notification signal is preferably one that identifies target human A on the display screen of the user's information terminal showing the image captured by the imaging device (drone D), but it may simply output a display or sound indicating danger. Possible users include beach managers and lifeguards.

[0033] Next, the operation of the drowning determination system 1 will be described with reference to the flowchart of FIG.

[0034] First, when the detection unit 3 detects an exposed portion of the target human A above water in the series of time-series images X (S1: YES), the judgment unit 4 refers to the memory unit 2 and judges whether the target human A is drowning or about to drown based on the vertical change of the exposed portion detected in the series of time-series images X (S2).

[0035] When it is determined that "target human A is drowning or about to drown" (S2: YES), a warning signal is output by the warning unit 5 (S3). Based on this warning signal, lifeguards or others waiting on the shore can be dispatched to the target human A to rescue him or her quickly and efficiently.

[0036] As described above, in the drowning determination system 1 of this embodiment, multiple patterns of changes in the vertical direction of the exposed part of a person above the water when the person is drowning in water are stored in the memory unit 2, and by referring to the memory unit 2, the drowning of the target human A is determined based on the vertical changes in the exposed part detected in a series of time-series images X.

[0037] According to such a configuration, it is possible to detect a drowning person or a person who is about to drown with high certainty based on the characteristics specialized for drowning. Moreover, since it is automatically determined whether the target person A is drowning or about to drown, the user's labor in video surveillance is significantly reduced. Moreover, by using the detection unit 3 with high detection accuracy, it is possible to detect drowning that occurs at a distance that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal surveillance.

[0038] In addition, in the drowning determination system 1 according to this embodiment, the multiple patterns of changes in the vertical direction of the part of a person exposed above water include multiple patterns of changes in the vertical direction of the person's arms exposed above water.

[0039] With this configuration, arm movements, which are likely to move up and down most violently when a person is drowning in water, are also taken into account, making it possible to detect drowning or drowning people with a higher degree of certainty.

[0040] Moreover, in the drowning determination system 1 according to this embodiment, the notification signal is for identifying the target human A on the display screen of the user's information terminal on which the image captured by the imaging device (drone D) is displayed.

[0041] According to this configuration, lifeguards and others waiting on the shore can be dispatched to rescue the target person A quickly and efficiently.

[0042] Next, a drowning determination system 10 according to a second embodiment of the present invention will be described.

[0043] In the second embodiment, as shown in FIG. 4, the presence of waves W is taken into consideration and a person B who is likely to be swept away by the waves is detected.

[0044] As shown in FIG. 5, the drowning determination system 10 includes a storage unit 11, a detection unit 12, a calculation unit 13, a determination unit 14, and a notification unit 15.

[0045] The memory unit 11 stores the speed or size of waves that pose a high risk of drowning.

[0046] Whether a wave is dangerous or not is preferably stored by combining the wave speed and the wave size, but only one of them may be stored. Also, it may be stored as "if the wave speed (size) is above a certain value, it is dangerous regardless of the combination with the wave size (speed)".

[0047] The detection unit 12 detects waves W moving toward a coastline E and a target human B positioned between the waves W and the coastline E in a series of time-series images Y of the water surface captured by an imaging device (drone D).

[0048] It is possible to determine that a "wave W has been detected" when a white line-like object is detected extending over a predetermined distance in a direction approximately parallel to the coastline or the horizon and heading toward the coastline E.

[0049] In addition, when the boundary between the brown of the beach and the white of the waves that have reached the beach is detected, it may be determined that "coastline E has been detected."

[0050] The calculation unit 13 calculates a predicted speed and a predicted size of the detected wave W when it reaches the target human B.

[0051] At this time, the calculation unit 13 first judges whether the wave W will reach the target human B. For example, it is possible to judge whether the wave W is likely to reach the target human B based on a change in the positional relationship between the wave W and the target human B in the time-series image Y of multiple frames, a change in the relative speed between the wave W and the target human B, and a change in the distance from the target human B to the coastline E. For example, if the position of the target human B deviates from the traveling direction of the wave W, it can be judged that the wave W will not reach. Also, if the speed of the target human B is faster than the speed of the wave W, it can be judged that the wave W will not reach. Furthermore, if the target human B is likely to reach the coastline E before the wave W reaches the target human B, it can be judged that the wave W will not reach.

[0052] Then, when it is determined that the wave W will reach the target human B, a predicted speed and a predicted size of the wave W at the time of arrival are calculated. As the predicted speed, for example, it is considered to calculate the timing at which the wave W will reach the target human B based on the speed of the wave W in the time-series image Y of multiple frames and the speed of the target human B, and to use the speed at the arrival timing. Also, it is considered to calculate the predicted size based on, for example, the change (acceleration) in the magnitude of the wave W in the time-series image Y of multiple frames and the timing at which the wave W will reach the target human B.

[0053] Furthermore, since the positional relationship between the wave W and the target human B, the speed of the wave W, the speed of the target human B, the distance between the target human B and the coastline E, etc. are expected to change from moment to moment, it is preferable that calculations by the calculation unit 13 are constantly performed.

[0054] The determination unit 14 refers to the memory unit 11 and determines whether or not there is a high risk that the target human B will be swept away by the waves and drown, based on the calculated predicted speed or predicted size. In detail, if there is a wave speed or size stored in the memory unit 11 that matches the calculated predicted speed and predicted size to a predetermined degree or higher, it determines that "the target human B is at high risk of being swept away by the waves and drowning."

[0055] The notification unit 15 outputs a notification signal indicating danger when it is determined that "there is a high risk that the target human B will be swept away by the waves and drown." The notification signal is preferably one that identifies the target human B on the display screen of the user's information terminal showing the image captured by the imaging device (drone D), but it may simply output a display or sound indicating the danger. Possible users include beach managers and lifeguards.

[0056] Next, the operation of the drowning determination system 10 according to this embodiment will be described with reference to the flowchart of FIG.

[0057] First, when the detection unit 12 detects a wave W and a target human B in a series of time-series images Y (S11: YES), the calculation unit 13 calculates the predicted speed and predicted size of the wave W detected in the series of time-series images Y when it reaches the target human B (S12).

[0058] Next, the determination unit 14 refers to the storage unit 11 and determines whether or not there is a high risk of the target human B being swept away by the waves and drowning, based on the calculated predicted speed and predicted size (S13).

[0059] If it is determined that there is a high risk that the target person B will be swept away by the waves and drown (S13: YES), a warning signal is output by the warning unit 15 (S14). Based on this warning signal, lifeguards and others waiting on the coast can be dispatched to rescue the target person B quickly and efficiently.

[0060] As described above, in the drowning determination system 10 of this embodiment, the speed or size of waves that pose a high risk of a human being being swept away and drowning is stored in the memory unit 11, and by referring to the memory unit 11, it is determined whether or not the target human B is at high risk of being swept away by a wave and drowning, based on the predicted speed and predicted size when the detected wave W reaches the target human B.

[0061] According to this configuration, since the "predicted speed and predicted size when the detected wave W reaches the target human B" that is difficult to distinguish with the human eye is determined, it is possible to detect with high certainty a person who is at high risk of being swept away by the wave and drowning. In addition, since it is automatically determined whether the target human B is at high risk of being swept away by the wave and drowning, the user's labor in video monitoring is significantly reduced. In addition, by using the detection unit 12 with high detection accuracy, it is possible to detect drowning that occurs in a distant place that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal monitoring.

[0062] Next, a drowning determination system 20 according to a third embodiment of the present invention will be described.

[0063] In the third embodiment, a person at risk of being swept away by a rip current is detected.

[0064] As shown in Figure 7, when there is a pair of currents F1 heading toward the coastline E, a rip current refers to a current F2 that occurs between the pair of currents F1 and flows in a direction away from the coastline E. Rip currents tend to move slowly, but because they are slow, it can happen that "person C gets caught in the rip current and is swept away far from the coastline E without realizing it."

[0065] As shown in FIG. 8, the drowning determination system 20 includes a detection unit 21, a determination unit 22, and a notification unit .

[0066] The detection unit 21 detects a pair of currents F1 heading toward the coastline E and a target human C exposed from the water surface, which are captured in a series of time-series images Z of the water surface captured by an imaging device (drone D). The detection of the currents F1 heading toward the coastline E can be realized, for example, by detecting waves heading toward the coastline E (white line-shaped waves that extend over a predetermined distance in a direction substantially parallel to the coastline or the horizon and head toward the coastline E).

[0067] When the detected target human C is located between a pair of currents F1 and the distance L between the pair of currents F1 is within a predetermined distance, the determination unit 22 determines that "the target human C is at risk of being swept away by a rip current F2 occurring between the pair of currents F1." As the distance L, for example, it is possible to measure the distance between the end of a wave included in one current F1 and the end of a wave included in the other current F1. Rip currents usually occur with a width of about 10 meters to 30 meters, so the predetermined distance can be determined with reference to the said width of about 10 meters to 30 meters.

[0068] The notification unit 23 outputs a notification signal indicating danger when it is determined that "the target human C is at risk of being swept away by a rip current." The notification signal is preferably one that identifies the target human C on the display screen of the user's information terminal showing the image captured by the imaging device (drone D), but it may simply output a display or sound indicating the danger. Possible users include beach managers and lifeguards.

[0069] Next, the operation of the drowning determination system 20 according to this embodiment will be described with reference to the flowchart of FIG.

[0070] First, when the detection unit 21 detects a pair of flows F1 and a target human C (S21: YES), the judgment unit 22 determines whether the target human C is located between the pair of flows F1 and whether the distance L between the pair of flows F1 is within a predetermined distance (S22).

[0071] If the target human C is located between the pair of currents F1 and the distance L between the pair of currents F1 is within a predetermined distance (S22: YES), it is determined that "the target human C is at risk of being swept away by the rip current F2" (S23), and a warning signal is output by the warning unit 23 (S24). Based on this warning signal, lifeguards or the like waiting on the coast can be dispatched to rescue the target human C quickly and efficiently.

[0072] As described above, in the drowning determination system 20 of this embodiment, when the target human C is located between a pair of currents F1 and the distance L between the pair of currents F1 is within a predetermined distance, it is determined that the target human C is at risk of being swept away by the rip current F2.

[0073] According to such a configuration, it is possible to grasp the occurrence of a rip current F2 that is difficult to distinguish with the human eye, and therefore it is possible to detect with high certainty a person who is at risk of being swept away by the rip current F2. In addition, since it is automatically determined whether or not the target person C is at risk of being swept away by the rip current F2, the user's labor in video surveillance is significantly reduced. In addition, by using the detection unit 21 with high detection accuracy, it is possible to detect a rip current F2 that occurs far away and cannot be detected by the human eye. Furthermore, by photographing a plurality of different water surfaces with a plurality of imaging devices, or by using a drone as the imaging device, it is possible to detect a rip current F2 that occurs in a place that cannot be detected by normal surveillance.

[0074] Next, a drowning determination system 30 according to a fourth embodiment of the present invention will be described.

[0075] In the fourth embodiment, as shown in FIG. 10, it is determined whether a target human G is drowning or about to drown based on ripples or blisters around the target human G.

[0076] As shown in FIG. 11, the drowning determination system 30 includes a storage unit 31, a detection unit 32, a determination unit 33, and a notification unit .

[0077] The memory unit 31 stores a plurality of patterns of ripples or bubbles on the water surface around a human being relative to the position of the human being when the human being is drowning in water.

[0078] Possible patterns of ripples or bubbles include "ripples with a radius of XX m centered on the human", "ripples centered on a position within a specified distance from the human", "large bubbles (splashes) at a position within a specified distance from the human", "small bubbles (splashes) at a position within a specified distance from the human", etc. The above-mentioned specified distance can be set based on the position where a human's outstretched hand hits the water.

[0079] In this embodiment, the storage unit 31 further stores a pattern of arm movement of a person when the person is drowning in water in association with a plurality of patterns of ripples or bubbles.

[0080] Possible arm movement patterns include "flapping with the elbow extended," "flapping with the elbow bent," "flapping alternately from left to right," and so on.

[0081] The detection unit 32 detects the exposed portion of the target human G above the water, and ripples or bubbles on the water surface surrounding the exposed portion, captured in a series of time-series images V of the water surface captured by an imaging device (drone D).

[0082] This detection may be performed using well-known posture determination techniques, tracking techniques, etc. It is preferable that the detection unit 32 obtains a series of time-series images V in approximately real time, and performs the above detection in approximately real time.

[0083] In addition, the boundary between the exposed part of the subject human G above the water and the sea surface can be determined based on the color boundary (the sea surface is blue, and the human's skin or hair color, etc.).

[0084] The determination unit 33 refers to the storage unit 31 and determines whether the target human G is drowning or about to drown, based on the positions of the exposed parts and the ripples or blisters detected in the series of time-series images V. In detail, when there is one among the multiple patterns stored in the storage unit 31 that has a predetermined degree of match or higher with the positions of the detected exposed parts and the ripples or blisters, it determines that "the target human G is drowning or about to drown."

[0085] In particular, in this embodiment, the judgment unit 33 refers to the memory unit 31 and takes into consideration the arm movements detected in the series of time-series images V to judge whether the target human G is drowning or about to drown.

[0086] The notification unit 34 outputs a notification signal indicating danger when it is determined that the target human G is drowning or about to drown. The notification signal is preferably one that identifies the target human G on the display screen of the user's information terminal showing the image captured by the imaging device (drone D), but it may simply output a display or sound indicating danger. Possible users include beach managers and lifeguards.

[0087] Next, the operation of the drowning determination system 30 will be described with reference to the flowchart of FIG.

[0088] First, when the detection unit 32 detects an exposed portion of the target human G above the water and ripples or bubbles on the water surface surrounding the exposed portion in the series of time-series images V (S31: YES), the judgment unit 33 refers to the memory unit 31 and judges whether the target human G is drowning or about to drown based on the position of the exposed portion and the ripples or bubbles detected in the series of time-series images V (S32).

[0089] When it is determined that the target human G is drowning or about to drown (S32: YES), a notification signal is output by the notification unit 34 (S33). Based on this notification signal, lifeguards or others waiting on the shore can be dispatched to the target human G to rescue him or her quickly and efficiently.

[0090] As described above, in the drowning determination system 30 of this embodiment, multiple patterns of ripples or bubbles on the water surface around a human being relative to the position of the human being when he or she is drowning in water are stored in the memory unit 31, and by referring to the memory unit 31, it is determined whether or not the target human being G is drowning or about to drown based on the position of the exposed part and the ripples or bubbles detected in the series of time-series images V.

[0091] According to this configuration, it is possible to detect a drowning person or a person who is about to drown with high certainty based on ripples or bubbles on the water surface around the person, which occur with a high probability when the person is drowning. In addition, since it is automatically determined whether the target person G is drowning or about to drown, the user's labor in video surveillance is significantly reduced. In addition, by using the detection unit 32 with high detection accuracy, it is possible to detect drowning that occurs in a distant place that cannot be detected by the human eye. Furthermore, by photographing multiple different water surfaces with multiple imaging devices or using a drone as the imaging device, it is possible to detect drowning that occurs in a place that cannot be detected by normal surveillance.

[0092] Moreover, the drowning determination system 30 according to this embodiment also takes into consideration the arm movements detected in the series of time-series images V to determine whether the target human G is drowning or about to drown.

[0093] With this configuration, arm movements, which are likely to be the most violent movements made by a person while drowning in water, are also taken into account, making it possible to detect drowning or drowning people with a higher degree of certainty.

[0094] The drowning determination system of the present invention is not limited to the above-described embodiment, and various modifications and improvements are possible within the scope of the claims.

[0095] For example, in the first embodiment, ripples or bubbles on the water surface around the target human A may be further taken into consideration.

[0096] In this case, the memory unit 2 further stores multiple patterns of ripples or bubbles on the water surface around the human A when he or she is drowning in water, in association with multiple patterns of changes in the upward and downward directions of the exposed parts described above, and the detection unit 3 further detects ripples or bubbles on the water surface around the subject human A captured in the series of time-series images X.

[0097] For example, it is thought that a change in the vertical direction of the torso (up and down movement) will generate ripples according to the magnitude and speed of the change, and a change in the vertical direction of an arm will generate ripples and bubbles according to the magnitude and speed of the change at the position on the water surface where the arm repeatedly goes under and underwater.

[0098] Then, the determination unit 4 refers to the storage unit 2 and determines whether the target human A is drowning or about to drown, taking into consideration the ripples or bubbles on the water surface detected in the series of time-series images X. In detail, if there is one among the multiple patterns stored in the storage unit 2 that has a predetermined degree of agreement or higher with the detected combination of "changes in the vertical direction of the exposed part" and "ripples or bubbles", it is determined that "the target human A is drowning or about to drown."

[0099] In this way, by taking into account ripples or bubbles on the water surface around the target human A, it is possible to detect a drowning person or a person who is about to drown with a higher degree of certainty.

[0100] In the first embodiment, the direction of the face of the target human A may be further taken into consideration.

[0101] In this case, the memory unit 2 further stores patterns of facial orientation when a person is drowning underwater in association with multiple patterns of changes in the upward and downward directions of the exposed parts described above, and the detection unit 3 further detects the facial orientation of the subject human A underwater reflected in the series of time-series images X.

[0102] For example, if the person is "looking up" or "facing forward," it is likely that the person is struggling, and therefore there is a high possibility that the exposed parts (both torso and arms) will have changed significantly in the vertical direction. On the other hand, if the person is "looking down," it is likely that the person is unconscious, and therefore there is a high possibility that the exposed parts (both torso and arms) will have changed very little in the vertical direction.

[0103] Then, the determination unit 4 refers to the storage unit 2 and determines whether the target human A is drowning or about to drown, taking into consideration the facial orientation detected in the series of time-series images X. In detail, if there is a combination of the detected "change in the vertical direction of the exposed part" and "facial orientation" that matches a predetermined degree or higher among the multiple patterns stored in the storage unit 2, it is determined that "the target human A is drowning or about to drown."

[0104] In this way, by taking into consideration the direction of the face of the target person A, it is possible to detect a drowning person or a person who is about to drown with a higher degree of certainty.

[0105] In the first embodiment, humans other than the target human A may also be taken into consideration.

[0106] In this case, the detection unit 3 further detects other humans who appear in the series of time-series images X, and the judgment unit 4 judges whether the target human A is drowning or about to drown, taking into account the distance between the target human A and the other humans or any variation in the distance.

[0107] For example, if another human is detected near the target human A (e.g., within a first specified distance), it may be that the situation is one in which children are playing, and in this case, it may be possible to reduce the probability of determining that the human is "drowning or about to drown."

[0108] On the other hand, if no other human is detected near the target human A (for example, within a second predetermined distance), it is possible to increase the probability of determining that the target human A is "drowning or about to drown."

[0109] In addition, if another human is detected approaching target human A at a speed greater than a predetermined value, it is possible that a rescue attempt is underway; in this case, it is possible to increase the probability of determining that the person is "drowning or near drowning."

[0110] In this way, by taking into consideration people other than the target person A, it is possible to detect people who are drowning or about to drown with a higher degree of certainty.

[0111] In the first embodiment, the distance from the target human A to the coastline E may be further taken into consideration.

[0112] In this case, the detection unit 3 further detects a coastline E captured in the series of time-series images X, and the judgment unit 4 judges whether the target human A is drowning or about to drown, taking into account the distance from the target human A to the coastline E.

[0113] For example, if the distance from the target human A to the coastline E is close (e.g., within a third specified distance), it is possible that a child is playing, and in this case, it is possible to reduce the probability of determining that the person is "drowning or about to drown."

[0114] On the other hand, when the distance from the target human A to the coastline E is long (for example, equal to or greater than a fourth predetermined distance), it is possible to increase the probability of determining that the target human A is "drowning or about to drown."

[0115] In this way, by taking into consideration the distance from the target human A to the coastline E, it is possible to detect a drowning person or a person who is about to drown with a higher degree of certainty.

[0116] In the first embodiment, the change in the vertical direction of the human arm exposed above the water is considered, but the change in the horizontal direction of the human arm exposed above the water may also be considered. In particular, in the above-mentioned example considering ripples or bubbles on the water surface around the subject human A, ripples and bubbles are generated at the position where the arm on the water surface repeatedly appears and disappears, depending on the magnitude and speed of the change, so it is effective to also consider the change in the horizontal direction of the arm.

[0117] In addition, in the above embodiment, a person who is drowning or who is about to drown was detected from video footage (a series of time-series images X) captured by drone D, but a person who is drowning or who is about to drown may also be detected from video footage captured by a camera installed on a beach or the like.

[0118] In addition, when shooting with a drone, human movements are detected as moving at a speed relative to the flight speed of the drone, so the detected movements may be significantly different from the various patterns stored in the memory unit. Therefore, when shooting with a moving object such as a drone, a sensor capable of detecting its own speed and moving direction, such as a gyro sensor, may be provided on the moving object so that human movements are determined by absolute speed. Conversely, patterns corresponding to a plurality of relative speeds may be stored in the memory unit, and human movements may be determined based on the patterns corresponding to the relative speeds, thereby making it possible to accurately determine human movements.

[0119] The present invention can also be applied to a program or method corresponding to the processing performed by the drowning determination system, and a recording medium storing the program. In the case of a recording medium, the program is installed in a computer or the like. Here, the recording medium storing the program may be a non-transient recording medium. A CD-ROM or the like is considered as a non-transient recording medium, but is not limited thereto. [Explanation of symbols]

[0120] 1, 10, 20, 30 Judgment System 2, 11, 31 storage section 3, 12, 21, 32 Detector 4, 14, 22, 33 Judgment section 5, 15, 23, 34 Notification Department 13 Calculation section A, B, C, G Target Humans D. Filming equipment (drone) E. Coastline F1 Trends F2 Rip current L distance W wave X, Y, Z, V time series images

Claims

1. A memory unit that stores a plurality of patterns of changes in the vertical direction of an exposed part of a human being above water when the human being is drowning in water; a detection unit that detects an exposed portion of a target human being above water in a series of time-series images of the water surface captured by an imaging device; a determination unit that refers to the storage unit and determines whether the target human is drowning or about to drown based on a change in an up-down direction of an exposed portion detected in the series of time-series images; a notification unit that outputs a notification signal when the determination unit determines that the target human is drowning or about to drown; Equipped with The detection unit further detects other humans appearing in the series of time-series images, A drowning determination system characterized in that the determination unit determines whether the target human is drowning or about to drown, taking into account the distance between the target human and the other human or a variation in the distance.

2. The plurality of patterns of changes in the vertical direction of the exposed portion of the human body above the water include a plurality of patterns of changes in the vertical direction of the exposed arm of the human body above the water, The detection unit detects an arm of a target human being exposed above the water in a series of time-series images, The drowning determination system of claim 1, characterized in that the determination unit refers to the memory unit and determines whether the target human is drowning or about to drown based on changes in the up and down direction of the arm detected in the series of time-series images.

3. the memory unit further stores a plurality of patterns of ripples or bubbles on the water surface around the human being when the human being is drowning in water, in association with the plurality of patterns; The detection unit further detects ripples or bubbles on the water surface around the target human being captured in the series of time-series images, The drowning determination system described in claim 1 or 2, characterized in that the determination unit refers to the memory unit and determines whether the target human is drowning or about to drown, taking into account ripples or bubbles on the water surface detected in the series of time-series images.

4. The detection unit further detects a coastline captured in the series of time-series images, The drowning determination system according to claim 1 , wherein the determination unit determines whether the target human is drowning or about to drown, taking into consideration a distance from the target human to the coastline.

5. The drowning determination system according to claim 1 , wherein the alarm signal is for identifying the target human on a display screen of a user's information terminal on which the image captured by the imaging device is displayed.

6. A program installed on a computer in which a plurality of patterns of changes in the vertical direction of an exposed portion of a human being above water when the human being is drowning in water are stored, the program comprising: A step of detecting an exposed portion of a target human being above water in a series of time-series images of the water surface captured by an imaging device; determining, with reference to the computer, whether the target human is drowning or about to drown based on a change in the vertical direction of an exposed portion detected in the series of time-series images; outputting an alarm signal when it is determined that the target human is drowning or about to drown; Equipped with In the detecting step, other humans appearing in the series of time-series images are also detected, A drowning determination program characterized in that in the determination step, it is determined whether the target human is drowning or about to drown, taking into account the distance between the target human and the other human or a variation in the distance.

7. 1. A computer-implemented method in which a plurality of patterns of changes in vertical orientation of an exposed portion of a human body above water as the human body drowns in water are stored, the method comprising: A step of detecting an exposed portion of a target human being above water in a series of time-series images of the water surface captured by an imaging device; determining, with reference to the computer, whether the target human is drowning or about to drown based on a change in the vertical direction of an exposed portion detected in the series of time-series images; outputting an alarm signal when it is determined that the target human is drowning or about to drown; Equipped with In the detecting step, other humans appearing in the series of time-series images are also detected, A drowning determination method characterized in that in the determination step, it is determined whether the target human is drowning or about to drown, taking into account the distance between the target human and the other human or a variation in the distance.

Images